@inproceedings{cetinoglu-2016-turkish,
title = "A {T}urkish-{G}erman Code-Switching Corpus",
author = {{\c{C}}etino{\u{g}}lu, {\"O}zlem},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1667",
pages = "4215--4220",
abstract = "Bilingual communities often alternate between languages both in spoken and written communication. One such community, Germany residents of Turkish origin produce Turkish-German code-switching, by heavily mixing two languages at discourse, sentence, or word level. Code-switching in general, and Turkish-German code-switching in particular, has been studied for a long time from a linguistic perspective. Yet resources to study them from a more computational perspective are limited due to either small size or licence issues. In this work we contribute the solution of this problem with a corpus. We present a Turkish-German code-switching corpus which consists of 1029 tweets, with a majority of intra-sentential switches. We share different type of code-switching we have observed in our collection and describe our processing steps. The first step is data collection and filtering. This is followed by manual tokenisation and normalisation. And finally, we annotate data with word-level language identification information. The resulting corpus is available for research purposes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cetinoglu-2016-turkish">
<titleInfo>
<title>A Turkish-German Code-Switching Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Özlem</namePart>
<namePart type="family">Çetinoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Bilingual communities often alternate between languages both in spoken and written communication. One such community, Germany residents of Turkish origin produce Turkish-German code-switching, by heavily mixing two languages at discourse, sentence, or word level. Code-switching in general, and Turkish-German code-switching in particular, has been studied for a long time from a linguistic perspective. Yet resources to study them from a more computational perspective are limited due to either small size or licence issues. In this work we contribute the solution of this problem with a corpus. We present a Turkish-German code-switching corpus which consists of 1029 tweets, with a majority of intra-sentential switches. We share different type of code-switching we have observed in our collection and describe our processing steps. The first step is data collection and filtering. This is followed by manual tokenisation and normalisation. And finally, we annotate data with word-level language identification information. The resulting corpus is available for research purposes.</abstract>
<identifier type="citekey">cetinoglu-2016-turkish</identifier>
<location>
<url>https://aclanthology.org/L16-1667</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4215</start>
<end>4220</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Turkish-German Code-Switching Corpus
%A Çetinoğlu, Özlem
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F cetinoglu-2016-turkish
%X Bilingual communities often alternate between languages both in spoken and written communication. One such community, Germany residents of Turkish origin produce Turkish-German code-switching, by heavily mixing two languages at discourse, sentence, or word level. Code-switching in general, and Turkish-German code-switching in particular, has been studied for a long time from a linguistic perspective. Yet resources to study them from a more computational perspective are limited due to either small size or licence issues. In this work we contribute the solution of this problem with a corpus. We present a Turkish-German code-switching corpus which consists of 1029 tweets, with a majority of intra-sentential switches. We share different type of code-switching we have observed in our collection and describe our processing steps. The first step is data collection and filtering. This is followed by manual tokenisation and normalisation. And finally, we annotate data with word-level language identification information. The resulting corpus is available for research purposes.
%U https://aclanthology.org/L16-1667
%P 4215-4220
Markdown (Informal)
[A Turkish-German Code-Switching Corpus](https://aclanthology.org/L16-1667) (Çetinoğlu, LREC 2016)
ACL
- Özlem Çetinoğlu. 2016. A Turkish-German Code-Switching Corpus. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 4215–4220, Portorož, Slovenia. European Language Resources Association (ELRA).